diff --git a/week1/community-contributions/day5-challenge-psxom3.ipynb b/week1/community-contributions/day5-challenge-psxom3.ipynb new file mode 100644 index 0000000..6ad1e33 --- /dev/null +++ b/week1/community-contributions/day5-challenge-psxom3.ipynb @@ -0,0 +1,3340 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "a98030af-fcd1-4d63-a36e-38ba053498fa", + "metadata": {}, + "source": [ + "# A full business solution\n", + "\n", + "## Now we will take our project from Day 1 to the next level\n", + "\n", + "### BUSINESS CHALLENGE:\n", + "\n", + "Create a product that builds a Brochure for a company to be used for prospective clients, investors and potential recruits.\n", + "\n", + "We will be provided a company name and their primary website.\n", + "\n", + "See the end of this notebook for examples of real-world business applications.\n", + "\n", + "And remember: I'm always available if you have problems or ideas! Please do reach out." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d5b08506-dc8b-4443-9201-5f1848161363", + "metadata": {}, + "outputs": [], + "source": [ + "# imports\n", + "# If these fail, please check you're running from an 'activated' environment with (llms) in the command prompt\n", + "\n", + "import os\n", + "import requests\n", + "import json\n", + "from typing import List\n", + "from dotenv import load_dotenv\n", + "from bs4 import BeautifulSoup\n", + "from IPython.display import Markdown, display, update_display\n", + "from openai import OpenAI" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fc5d8880-f2ee-4c06-af16-ecbc0262af61", + "metadata": {}, + "outputs": [], + "source": [ + "# Initialize and constants\n", + "\n", + "load_dotenv(override=True)\n", + "api_key = os.getenv('OPENAI_API_KEY')\n", + "\n", + "if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:\n", + " print(\"API key looks good so far\")\n", + "else:\n", + " print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n", + " \n", + "MODEL = 'gpt-4o-mini'\n", + "openai = OpenAI()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "106dd65e-90af-4ca8-86b6-23a41840645b", + "metadata": {}, + "outputs": [], + "source": [ + "# A class to represent a Webpage\n", + "\n", + "# Some websites need you to use proper headers when fetching them:\n", + "headers = {\n", + " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n", + "}\n", + "\n", + "class Website:\n", + " \"\"\"\n", + " A utility class to represent a Website that we have scraped, now with links\n", + " \"\"\"\n", + "\n", + " def __init__(self, url):\n", + " self.url = url\n", + " response = requests.get(url, headers=headers)\n", + " self.body = response.content\n", + " soup = BeautifulSoup(self.body, 'html.parser')\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + " if soup.body:\n", + " for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + " self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", + " else:\n", + " self.text = \"\"\n", + " links = [link.get('href') for link in soup.find_all('a')]\n", + " self.links = [link for link in links if link]\n", + "\n", + " def get_contents(self):\n", + " return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e30d8128-933b-44cc-81c8-ab4c9d86589a", + "metadata": {}, + "outputs": [], + "source": [ + "ed = Website(\"https://edwarddonner.com\")\n", + "ed.links" + ] + }, + { + "cell_type": "markdown", + "id": "1771af9c-717a-4fca-bbbe-8a95893312c3", + "metadata": {}, + "source": [ + "## First step: Have GPT-4o-mini figure out which links are relevant\n", + "\n", + "### Use a call to gpt-4o-mini to read the links on a webpage, and respond in structured JSON. \n", + "It should decide which links are relevant, and replace relative links such as \"/about\" with \"https://company.com/about\". \n", + "We will use \"one shot prompting\" in which we provide an example of how it should respond in the prompt.\n", + "\n", + "This is an excellent use case for an LLM, because it requires nuanced understanding. Imagine trying to code this without LLMs by parsing and analyzing the webpage - it would be very hard!\n", + "\n", + "Sidenote: there is a more advanced technique called \"Structured Outputs\" in which we require the model to respond according to a spec. We cover this technique in Week 8 during our autonomous Agentic AI project." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6957b079-0d96-45f7-a26a-3487510e9b35", + "metadata": {}, + "outputs": [], + "source": [ + "link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n", + "You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n", + "such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n", + "link_system_prompt += \"You should respond in JSON as in this example:\"\n", + "link_system_prompt += \"\"\"\n", + "{\n", + " \"links\": [\n", + " {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n", + " {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n", + " ],\n", + "}\n", + "\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "id": "a19e4ac5-73c0-49ed-9472-05b0955e93df", + "metadata": {}, + "outputs": [], + "source": [ + "# Multi-shot prompting for selecting relevant links\n", + "link_system_prompt = \"\"\"\n", + "You are provided with a list of links found on a webpage. \n", + "Your task is to decide which of these links are most relevant for a company brochure. \n", + "Relevant links typically include an About page, Careers page, Products page, or Contact page.\n", + "You should always respond in the following JSON format:\n", + "\n", + "Example 1:\n", + "{\n", + " \"links\": [\n", + " {\"type\": \"about page\", \"url\": \"https://company.com/about\"},\n", + " {\"type\": \"careers page\", \"url\": \"https://company.com/careers\"}\n", + " ]\n", + "}\n", + "\n", + "Example 2:\n", + "{\n", + " \"links\": [\n", + " {\"type\": \"products page\", \"url\": \"https://company.com/products\"},\n", + " {\"type\": \"contact page\", \"url\": \"https://company.com/contact\"}\n", + " ]\n", + "}\n", + "\n", + "Now, analyze the provided links and generate a response following this format.\n", + "\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "id": "b97e4068-97ed-4120-beae-c42105e4d59a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "You are provided with a list of links found on a webpage. \n", + "Your task is to decide which of these links are most relevant for a company brochure. \n", + "Relevant links typically include an About page, Careers page, Products page, or Contact page.\n", + "You should always respond in the following JSON format:\n", + "\n", + "Example 1:\n", + "{\n", + " \"links\": [\n", + " {\"type\": \"about page\", \"url\": \"https://company.com/about\"},\n", + " {\"type\": \"careers page\", \"url\": \"https://company.com/careers\"}\n", + " ]\n", + "}\n", + "\n", + "Example 2:\n", + "{\n", + " \"links\": [\n", + " {\"type\": \"products page\", \"url\": \"https://company.com/products\"},\n", + " {\"type\": \"contact page\", \"url\": \"https://company.com/contact\"}\n", + " ]\n", + "}\n", + "\n", + "Now, analyze the provided links and generate a response following this format.\n", + "\n" + ] + } + ], + "source": [ + "print(link_system_prompt)" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "8e1f601b-2eaf-499d-b6b8-c99050c9d6b3", + "metadata": {}, + "outputs": [], + "source": [ + "def get_links_user_prompt(website):\n", + " user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n", + " user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n", + "Do not include Terms of Service, Privacy, email links.\\n\"\n", + " user_prompt += \"Links (some might be relative links):\\n\"\n", + " user_prompt += \"\\n\".join(website.links)\n", + " return user_prompt" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "id": "6bcbfa78-6395-4685-b92c-22d592050fd7", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Here is the list of links on the website of https://edwarddonner.com - please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. Do not include Terms of Service, Privacy, email links.\n", + "Links (some might be relative links):\n", + "https://edwarddonner.com/\n", + "https://edwarddonner.com/connect-four/\n", + "https://edwarddonner.com/outsmart/\n", + "https://edwarddonner.com/about-me-and-about-nebula/\n", + "https://edwarddonner.com/posts/\n", + "https://edwarddonner.com/\n", + "https://news.ycombinator.com\n", + "https://nebula.io/?utm_source=ed&utm_medium=referral\n", + "https://www.prnewswire.com/news-releases/wynden-stark-group-acquires-nyc-venture-backed-tech-startup-untapt-301269512.html\n", + "https://patents.google.com/patent/US20210049536A1/\n", + "https://www.linkedin.com/in/eddonner/\n", + "https://edwarddonner.com/2025/01/23/llm-workshop-hands-on-with-agents-resources/\n", + "https://edwarddonner.com/2025/01/23/llm-workshop-hands-on-with-agents-resources/\n", + "https://edwarddonner.com/2024/12/21/llm-resources-superdatascience/\n", + "https://edwarddonner.com/2024/12/21/llm-resources-superdatascience/\n", + "https://edwarddonner.com/2024/11/13/llm-engineering-resources/\n", + "https://edwarddonner.com/2024/11/13/llm-engineering-resources/\n", + "https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/\n", + "https://edwarddonner.com/2024/10/16/from-software-engineer-to-ai-data-scientist-resources/\n", + "https://edwarddonner.com/\n", + "https://edwarddonner.com/connect-four/\n", + "https://edwarddonner.com/outsmart/\n", + "https://edwarddonner.com/about-me-and-about-nebula/\n", + "https://edwarddonner.com/posts/\n", + "mailto:hello@mygroovydomain.com\n", + "https://www.linkedin.com/in/eddonner/\n", + "https://twitter.com/edwarddonner\n", + "https://www.facebook.com/edward.donner.52\n" + ] + } + ], + "source": [ + "print(get_links_user_prompt(ed))" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "id": "a29aca19-ca13-471c-a4b4-5abbfa813f69", + "metadata": {}, + "outputs": [], + "source": [ + "def get_links(url):\n", + " website = Website(url)\n", + " response = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": link_system_prompt},\n", + " {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n", + " ],\n", + " response_format={\"type\": \"json_object\"}\n", + " )\n", + " result = response.choices[0].message.content\n", + " return json.loads(result)" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "id": "74a827a0-2782-4ae5-b210-4a242a8b4cc2", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['/',\n", + " '/models',\n", + " '/datasets',\n", + " '/spaces',\n", + " '/posts',\n", + " '/docs',\n", + " '/enterprise',\n", + " '/pricing',\n", + " '/login',\n", + " '/join',\n", + " '/spaces',\n", + " '/models',\n", + " '/Qwen/Qwen2.5-Omni-7B',\n", + " '/deepseek-ai/DeepSeek-V3-0324',\n", + " '/all-hands/openhands-lm-32b-v0.1',\n", + " '/manycore-research/SpatialLM-Llama-1B',\n", + " '/ByteDance/MegaTTS3',\n", + " '/models',\n", + " '/spaces/enzostvs/deepsite',\n", + " '/spaces/jamesliu1217/EasyControl_Ghibli',\n", + " '/spaces/ByteDance/InfiniteYou-FLUX',\n", + " '/spaces/VAST-AI/TripoSG',\n", + " '/spaces/Stable-X/Hi3DGen',\n", + " '/spaces',\n", + " '/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset-v1',\n", + " '/datasets/FreedomIntelligence/medical-o1-reasoning-SFT',\n", + " '/datasets/glaiveai/reasoning-v1-20m',\n", + " '/datasets/a-m-team/AM-DeepSeek-R1-Distilled-1.4M',\n", + " '/datasets/Anthropic/EconomicIndex',\n", + " '/datasets',\n", + " '/join',\n", + " '/pricing#endpoints',\n", + " '/pricing#spaces',\n", + " '/pricing',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/enterprise',\n", + " '/allenai',\n", + " '/facebook',\n", + " '/amazon',\n", + " '/google',\n", + " '/Intel',\n", + " '/microsoft',\n", + " '/grammarly',\n", + " '/Writer',\n", + " '/docs/transformers',\n", + " '/docs/diffusers',\n", + " '/docs/safetensors',\n", + " '/docs/huggingface_hub',\n", + " '/docs/tokenizers',\n", + " '/docs/trl',\n", + " '/docs/transformers.js',\n", + " '/docs/smolagents',\n", + " '/docs/peft',\n", + " '/docs/datasets',\n", + " '/docs/text-generation-inference',\n", + " '/docs/accelerate',\n", + " '/models',\n", + " '/datasets',\n", + " '/spaces',\n", + " '/tasks',\n", + " 'https://ui.endpoints.huggingface.co',\n", + " '/chat',\n", + " '/huggingface',\n", + " '/brand',\n", + " '/terms-of-service',\n", + " '/privacy',\n", + " 'https://apply.workable.com/huggingface/',\n", + " 'mailto:press@huggingface.co',\n", + " '/learn',\n", + " '/docs',\n", + " '/blog',\n", + " 'https://discuss.huggingface.co',\n", + " 'https://status.huggingface.co/',\n", + " 'https://github.com/huggingface',\n", + " 'https://twitter.com/huggingface',\n", + " 'https://www.linkedin.com/company/huggingface/',\n", + " '/join/discord']" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Anthropic has made their site harder to scrape, so I'm using HuggingFace..\n", + "\n", + "huggingface = Website(\"https://huggingface.co\")\n", + "huggingface.links" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "id": "d3d583e2-dcc4-40cc-9b28-1e8dbf402924", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'links': [{'type': 'about page', 'url': 'https://huggingface.co/huggingface'},\n", + " {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'},\n", + " {'type': 'products page', 'url': 'https://huggingface.co/models'},\n", + " {'type': 'datasets page', 'url': 'https://huggingface.co/datasets'},\n", + " {'type': 'contact page', 'url': 'https://huggingface.co/contact'}]}" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "get_links(\"https://huggingface.co\")" + ] + }, + { + "cell_type": "markdown", + "id": "0d74128e-dfb6-47ec-9549-288b621c838c", + "metadata": {}, + "source": [ + "## Second step: make the brochure!\n", + "\n", + "Assemble all the details into another prompt to GPT4-o" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "id": "85a5b6e2-e7ef-44a9-bc7f-59ede71037b5", + "metadata": {}, + "outputs": [], + "source": [ + "def get_all_details(url):\n", + " result = \"Landing page:\\n\"\n", + " result += Website(url).get_contents()\n", + " links = get_links(url)\n", + " print(\"Found links:\", links)\n", + " for link in links[\"links\"]:\n", + " result += f\"\\n\\n{link['type']}\\n\"\n", + " result += Website(link[\"url\"]).get_contents()\n", + " return result" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "id": "5099bd14-076d-4745-baf3-dac08d8e5ab2", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/huggingface'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'products page', 'url': 'https://huggingface.co/models'}, {'type': 'products page', 'url': 'https://huggingface.co/datasets'}, {'type': 'products page', 'url': 'https://huggingface.co/spaces'}, {'type': 'contact page', 'url': 'https://discuss.huggingface.co'}, {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'}]}\n", + "Landing page:\n", + "Webpage Title:\n", + "Hugging Face – The AI community building the future.\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "The AI community building the future.\n", + "The platform where the machine learning community collaborates on models, datasets, and applications.\n", + "Explore AI Apps\n", + "or\n", + "Browse 1M+ models\n", + "Trending on\n", + "this week\n", + "Models\n", + "Qwen/Qwen2.5-Omni-7B\n", + "Updated\n", + "3 days ago\n", + "•\n", + "70.7k\n", + "•\n", + "1.1k\n", + "deepseek-ai/DeepSeek-V3-0324\n", + "Updated\n", + "7 days ago\n", + "•\n", + "143k\n", + "•\n", + "2.26k\n", + "all-hands/openhands-lm-32b-v0.1\n", + "Updated\n", + "3 days ago\n", + "•\n", + "2.39k\n", + "•\n", + "192\n", + "manycore-research/SpatialLM-Llama-1B\n", + "Updated\n", + "13 days ago\n", + "•\n", + "13.8k\n", + "•\n", + "885\n", + "ByteDance/MegaTTS3\n", + "Updated\n", + "about 5 hours ago\n", + "•\n", + "162\n", + "Browse 1M+ models\n", + "Spaces\n", + "Running\n", + "1.95k\n", + "1.95k\n", + "DeepSite\n", + "🐳\n", + "Generate any application with DeepSeek\n", + "Running\n", + "on\n", + "Zero\n", + "365\n", + "365\n", + "EasyControl Ghibli\n", + "🦀\n", + "New Ghibli EasyControl model is now released!!\n", + "Running\n", + "on\n", + "Zero\n", + "737\n", + "737\n", + "InfiniteYou-FLUX\n", + "📸\n", + "Flexible Photo Recrafting While Preserving Your Identity\n", + "Running\n", + "on\n", + "Zero\n", + "268\n", + "268\n", + "TripoSG\n", + "🔮\n", + "Generate 3D models from images\n", + "Running\n", + "on\n", + "Zero\n", + "254\n", + "254\n", + "Hi3DGen\n", + "🏢\n", + "High-fidelity 3D Geometry Generation from images\n", + "Browse 400k+ applications\n", + "Datasets\n", + "nvidia/Llama-Nemotron-Post-Training-Dataset-v1\n", + "Updated\n", + "16 days ago\n", + "•\n", + "10.9k\n", + "•\n", + "300\n", + "FreedomIntelligence/medical-o1-reasoning-SFT\n", + "Updated\n", + "Feb 22\n", + "•\n", + "24k\n", + "•\n", + "602\n", + "glaiveai/reasoning-v1-20m\n", + "Updated\n", + "15 days ago\n", + "•\n", + "8.87k\n", + "•\n", + "156\n", + "a-m-team/AM-DeepSeek-R1-Distilled-1.4M\n", + "Updated\n", + "4 days ago\n", + "•\n", + "8.59k\n", + "•\n", + "102\n", + "Anthropic/EconomicIndex\n", + "Updated\n", + "7 days ago\n", + "•\n", + "3.5k\n", + "•\n", + "242\n", + "Browse 250k+ datasets\n", + "The Home of Machine Learning\n", + "Create, discover and collaborate on ML better.\n", + "The collaboration platform\n", + "Host and collaborate on unlimited public models, datasets and applications.\n", + "Move faster\n", + "With the HF Open source stack.\n", + "Explore all modalities\n", + "Text, image, video, audio or even 3D.\n", + "Build your portfolio\n", + "Share your work with the world and build your ML profile.\n", + "Sign Up\n", + "Accelerate your ML\n", + "We provide paid Compute and Enterprise solutions.\n", + "Compute\n", + "Deploy on optimized\n", + "Inference Endpoints\n", + "or update your\n", + "Spaces applications\n", + "to a GPU in a few clicks.\n", + "View pricing\n", + "Starting at $0.60/hour for GPU\n", + "Enterprise\n", + "Give your team the most advanced platform to build AI with enterprise-grade security, access controls and\n", + "\t\t\tdedicated support.\n", + "Getting started\n", + "Starting at $20/user/month\n", + "Single Sign-On\n", + "Regions\n", + "Priority Support\n", + "Audit Logs\n", + "Resource Groups\n", + "Private Datasets Viewer\n", + "More than 50,000 organizations are using Hugging Face\n", + "Ai2\n", + "Enterprise\n", + "non-profit\n", + "•\n", + "396 models\n", + "•\n", + "3k followers\n", + "AI at Meta\n", + "Enterprise\n", + "company\n", + "•\n", + "2.07k models\n", + "•\n", + "5.34k followers\n", + "Amazon\n", + "company\n", + "•\n", + "10 models\n", + "•\n", + "2.94k followers\n", + "Google\n", + "company\n", + "•\n", + "982 models\n", + "•\n", + "10.9k followers\n", + "Intel\n", + "company\n", + "•\n", + "219 models\n", + "•\n", + "2.39k followers\n", + "Microsoft\n", + "company\n", + "•\n", + "365 models\n", + "•\n", + "10.8k followers\n", + "Grammarly\n", + "Enterprise\n", + "company\n", + "•\n", + "10 models\n", + "•\n", + "148 followers\n", + "Writer\n", + "Enterprise\n", + "company\n", + "•\n", + "21 models\n", + "•\n", + "254 followers\n", + "Our Open Source\n", + "We are building the foundation of ML tooling with the community.\n", + "Transformers\n", + "142,379\n", + "State-of-the-art ML for PyTorch, TensorFlow, JAX\n", + "Diffusers\n", + "28,402\n", + "State-of-the-art Diffusion models in PyTorch\n", + "Safetensors\n", + "3,202\n", + "Safe way to store/distribute neural network weights\n", + "Hub Python Library\n", + "2,486\n", + "Python client to interact with the Hugging Face Hub\n", + "Tokenizers\n", + "9,555\n", + "Fast tokenizers optimized for research & production\n", + "TRL\n", + "13,008\n", + "Train transformers LMs with reinforcement learning\n", + "Transformers.js\n", + "13,349\n", + "State-of-the-art ML running directly in your browser\n", + "smolagents\n", + "16,320\n", + "Smol library to build great agents in Python\n", + "PEFT\n", + "17,998\n", + "Parameter-efficient finetuning for large language models\n", + "Datasets\n", + "19,925\n", + "Access & share datasets for any ML tasks\n", + "Text Generation Inference\n", + "9,961\n", + "Serve language models with TGI optimized toolkit\n", + "Accelerate\n", + "8,571\n", + "Train PyTorch models with multi-GPU, TPU, mixed precision\n", + "System theme\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Tasks\n", + "Inference Endpoints\n", + "HuggingChat\n", + "Company\n", + "About\n", + "Brand assets\n", + "Terms of service\n", + "Privacy\n", + "Jobs\n", + "Press\n", + "Resources\n", + "Learn\n", + "Documentation\n", + "Blog\n", + "Forum\n", + "Service Status\n", + "Social\n", + "GitHub\n", + "Twitter\n", + "LinkedIn\n", + "Discord\n", + "\n", + "\n", + "\n", + "about page\n", + "Webpage Title:\n", + "huggingface (Hugging Face)\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Hugging Face\n", + "Enterprise\n", + "company\n", + "Verified\n", + "https://huggingface.co\n", + "huggingface\n", + "huggingface\n", + "Activity Feed\n", + "Follow\n", + "29,451\n", + "AI & ML interests\n", + "The AI community building the future.\n", + "Recent Activity\n", + "stevhliu\n", + "new\n", + "activity\n", + "about 19 hours ago\n", + "huggingface/documentation-images:\n", + "add attention mask image for code_llama\n", + "giadap\n", + "authored\n", + "a paper\n", + "about 23 hours ago\n", + "Bridging the Gap: Integrating Ethics and Environmental Sustainability in\n", + " AI Research and Practice\n", + "mishig\n", + "updated\n", + "a Space\n", + "1 day ago\n", + "huggingface/inference-playground\n", + "View all activity\n", + "Articles\n", + "Yay! Organizations can now publish blog Articles\n", + "Jan 20\n", + "•\n", + "38\n", + "Team members\n", + "212\n", + "+178\n", + "+165\n", + "+144\n", + "+134\n", + "+114\n", + "Organization Card\n", + "Community\n", + "About org cards\n", + "👋 Hi!\n", + "We are on a mission to democratize\n", + "good\n", + "machine learning, one commit at a time.\n", + "If that sounds like something you should be doing, why don't you\n", + "join us\n", + "!\n", + "For press enquiries, you can\n", + "✉️ contact our team here\n", + ".\n", + "Collections\n", + "1\n", + "DistilBERT release\n", + "Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.\n", + "distilbert/distilbert-base-cased\n", + "Fill-Mask\n", + "•\n", + "Updated\n", + "May 6, 2024\n", + "•\n", + "489k\n", + "•\n", + "•\n", + "39\n", + "distilbert/distilbert-base-uncased\n", + "Fill-Mask\n", + "•\n", + "Updated\n", + "May 6, 2024\n", + "•\n", + "12.1M\n", + "•\n", + "•\n", + "656\n", + "distilbert/distilbert-base-multilingual-cased\n", + "Fill-Mask\n", + "•\n", + "Updated\n", + "May 6, 2024\n", + "•\n", + "2.26M\n", + "•\n", + "•\n", + "184\n", + "distilbert/distilbert-base-uncased-finetuned-sst-2-english\n", + "Text Classification\n", + "•\n", + "Updated\n", + "Dec 19, 2023\n", + "•\n", + "6.84M\n", + "•\n", + "•\n", + "727\n", + "spaces\n", + "26\n", + "Sort: \n", + "\t\tRecently updated\n", + "pinned\n", + "Running\n", + "81\n", + "Number Tokenization Blog\n", + "📈\n", + "Explore how tokenization affects arithmetic in LLMs\n", + "huggingface\n", + "Dec 14, 2024\n", + "Running\n", + "137\n", + "Inference Playground\n", + "🔋\n", + "Set and update website theme based on user preference\n", + "huggingface\n", + "1 day ago\n", + "Running\n", + "1\n", + "Space Build\n", + "🐨\n", + "Generate static files for spaces\n", + "huggingface\n", + "6 days ago\n", + "Running\n", + "20\n", + "InferenceSupport\n", + "💥\n", + "Discussions about the Inference Providers feature on the Hub\n", + "huggingface\n", + "7 days ago\n", + "Running\n", + "350\n", + "AI Deadlines\n", + "⚡\n", + "Schedule tasks efficiently using AI-generated deadlines\n", + "huggingface\n", + "19 days ago\n", + "Running\n", + "533\n", + "Open Source Ai Year In Review 2024\n", + "😻\n", + "What happened in open-source AI this year, and what’s next?\n", + "huggingface\n", + "Jan 8\n", + "Expand 26\n", + "\t\t\t\t\t\t\tspaces\n", + "models\n", + "16\n", + "Sort: \n", + "\t\tRecently updated\n", + "huggingface/timesfm-tourism-monthly\n", + "Updated\n", + "3 days ago\n", + "•\n", + "56\n", + "•\n", + "2\n", + "huggingface/CodeBERTa-language-id\n", + "Text Classification\n", + "•\n", + "Updated\n", + "Mar 29, 2024\n", + "•\n", + "7.06k\n", + "•\n", + "•\n", + "59\n", + "huggingface/falcon-40b-gptq\n", + "Text Generation\n", + "•\n", + "Updated\n", + "Jun 14, 2023\n", + "•\n", + "14\n", + "•\n", + "12\n", + "huggingface/autoformer-tourism-monthly\n", + "Updated\n", + "May 24, 2023\n", + "•\n", + "44.6k\n", + "•\n", + "9\n", + "huggingface/distilbert-base-uncased-finetuned-mnli\n", + "Text Classification\n", + "•\n", + "Updated\n", + "Mar 22, 2023\n", + "•\n", + "184\n", + "•\n", + "•\n", + "2\n", + "huggingface/informer-tourism-monthly\n", + "Updated\n", + "Feb 24, 2023\n", + "•\n", + "44.9k\n", + "•\n", + "6\n", + "huggingface/time-series-transformer-tourism-monthly\n", + "Updated\n", + "Feb 23, 2023\n", + "•\n", + "37.2k\n", + "•\n", + "20\n", + "huggingface/the-no-branch-repo\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "Feb 10, 2023\n", + "•\n", + "18\n", + "•\n", + "4\n", + "huggingface/CodeBERTa-small-v1\n", + "Fill-Mask\n", + "•\n", + "Updated\n", + "Jun 27, 2022\n", + "•\n", + "36.7k\n", + "•\n", + "80\n", + "huggingface/test-model-repo\n", + "Updated\n", + "Nov 19, 2021\n", + "•\n", + "1\n", + "Expand 16\n", + "\t\t\t\t\t\t\tmodels\n", + "datasets\n", + "42\n", + "Sort: \n", + "\t\tRecently updated\n", + "huggingface/documentation-images\n", + "Viewer\n", + "•\n", + "Updated\n", + "about 19 hours ago\n", + "•\n", + "52\n", + "•\n", + "3.79M\n", + "•\n", + "57\n", + "huggingface/transformers-metadata\n", + "Viewer\n", + "•\n", + "Updated\n", + "3 days ago\n", + "•\n", + "1.6k\n", + "•\n", + "963\n", + "•\n", + "20\n", + "huggingface/policy-docs\n", + "Updated\n", + "14 days ago\n", + "•\n", + "2.53k\n", + "•\n", + "10\n", + "huggingface/diffusers-metadata\n", + "Viewer\n", + "•\n", + "Updated\n", + "19 days ago\n", + "•\n", + "69\n", + "•\n", + "513\n", + "•\n", + "6\n", + "huggingface/gemini-results-2025-03-03\n", + "Viewer\n", + "•\n", + "Updated\n", + "about 1 month ago\n", + "•\n", + "17\n", + "•\n", + "64\n", + "huggingface/gemini-results-2025-02-28\n", + "Viewer\n", + "•\n", + "Updated\n", + "Mar 1\n", + "•\n", + "21\n", + "•\n", + "41\n", + "huggingface/gemini-results-2025-02-27\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 28\n", + "•\n", + "24\n", + "•\n", + "44\n", + "huggingface/gemini-results-2025-02-25\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 26\n", + "•\n", + "32\n", + "•\n", + "39\n", + "huggingface/gemini-results-2025-02-24\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 25\n", + "•\n", + "32\n", + "•\n", + "32\n", + "huggingface/gemini-results-2025-02-21\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 22\n", + "•\n", + "29\n", + "•\n", + "118\n", + "•\n", + "1\n", + "Expand 42\n", + "\t\t\t\t\t\t\tdatasets\n", + "System theme\n", + "Company\n", + "TOS\n", + "Privacy\n", + "About\n", + "Jobs\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Pricing\n", + "Docs\n", + "\n", + "\n", + "\n", + "careers page\n", + "Webpage Title:\n", + "Hugging Face - Current Openings\n", + "Webpage Contents:\n", + "\n", + "\n", + "\n", + "\n", + "products page\n", + "Webpage Title:\n", + "Models - Hugging Face\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Edit Models filters\n", + "Tasks\n", + "Libraries\n", + "Datasets\n", + "Languages\n", + "Licenses\n", + "Other\n", + "Multimodal\n", + "Audio-Text-to-Text\n", + "Image-Text-to-Text\n", + "Visual Question Answering\n", + "Document Question Answering\n", + "Video-Text-to-Text\n", + "Visual Document Retrieval\n", + "Any-to-Any\n", + "Computer Vision\n", + "Depth Estimation\n", + "Image Classification\n", + "Object Detection\n", + "Image Segmentation\n", + "Text-to-Image\n", + "Image-to-Text\n", + "Image-to-Image\n", + "Image-to-Video\n", + "Unconditional Image Generation\n", + "Video Classification\n", + "Text-to-Video\n", + "Zero-Shot Image Classification\n", + "Mask Generation\n", + "Zero-Shot Object Detection\n", + "Text-to-3D\n", + "Image-to-3D\n", + "Image Feature Extraction\n", + "Keypoint Detection\n", + "Natural Language Processing\n", + "Text Classification\n", + "Token Classification\n", + "Table Question Answering\n", + "Question Answering\n", + "Zero-Shot Classification\n", + "Translation\n", + "Summarization\n", + "Feature Extraction\n", + "Text Generation\n", + "Text2Text Generation\n", + "Fill-Mask\n", + "Sentence Similarity\n", + "Text Ranking\n", + "Audio\n", + "Text-to-Speech\n", + "Text-to-Audio\n", + "Automatic Speech Recognition\n", + "Audio-to-Audio\n", + "Audio Classification\n", + "Voice Activity Detection\n", + "Tabular\n", + "Tabular Classification\n", + "Tabular Regression\n", + "Time Series Forecasting\n", + "Reinforcement Learning\n", + "Reinforcement Learning\n", + "Robotics\n", + "Other\n", + "Graph Machine Learning\n", + "Apply filters\n", + "Models\n", + "Full-text search\n", + "Add filters\n", + "Sort: \n", + "\t\tTrending\n", + "Qwen/Qwen2.5-Omni-7B\n", + "Any-to-Any\n", + "•\n", + "Updated\n", + "3 days ago\n", + "•\n", + "70.7k\n", + "•\n", + "1.1k\n", + "deepseek-ai/DeepSeek-V3-0324\n", + "Text Generation\n", + "•\n", + "Updated\n", + "7 days ago\n", + "•\n", + "143k\n", + "•\n", + "•\n", + "2.26k\n", + "all-hands/openhands-lm-32b-v0.1\n", + "Text Generation\n", + "•\n", + "Updated\n", + "3 days ago\n", + "•\n", + "2.39k\n", + "•\n", + "192\n", + "manycore-research/SpatialLM-Llama-1B\n", + "Text Generation\n", + "•\n", + "Updated\n", + "13 days ago\n", + "•\n", + "13.8k\n", + "•\n", + "885\n", + "ByteDance/MegaTTS3\n", + "Updated\n", + "about 5 hours ago\n", + "•\n", + "162\n", + "openfree/flux-chatgpt-ghibli-lora\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "about 7 hours ago\n", + "•\n", + "3.62k\n", + "•\n", + "•\n", + "161\n", + "ds4sd/SmolDocling-256M-preview\n", + "Image-Text-to-Text\n", + "•\n", + "Updated\n", + "11 days ago\n", + "•\n", + "63.4k\n", + "•\n", + "1.12k\n", + "rasbt/llama-3.2-from-scratch\n", + "Updated\n", + "2 days ago\n", + "•\n", + "144\n", + "black-forest-labs/FLUX.1-dev\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "Aug 16, 2024\n", + "•\n", + "2.29M\n", + "•\n", + "•\n", + "9.66k\n", + "ByteDance/InfiniteYou\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "about 12 hours ago\n", + "•\n", + "457\n", + "•\n", + "526\n", + "hexgrad/Kokoro-82M\n", + "Text-to-Speech\n", + "•\n", + "Updated\n", + "16 days ago\n", + "•\n", + "1.87M\n", + "•\n", + "3.92k\n", + "deepseek-ai/DeepSeek-R1\n", + "Text Generation\n", + "•\n", + "Updated\n", + "7 days ago\n", + "•\n", + "1.4M\n", + "•\n", + "•\n", + "11.8k\n", + "sesame/csm-1b\n", + "Text-to-Speech\n", + "•\n", + "Updated\n", + "18 days ago\n", + "•\n", + "73.6k\n", + "•\n", + "•\n", + "1.78k\n", + "nitrosocke/Ghibli-Diffusion\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "Aug 3, 2023\n", + "•\n", + "60.5k\n", + "•\n", + "•\n", + "723\n", + "starvector/starvector-8b-im2svg\n", + "Text Generation\n", + "•\n", + "Updated\n", + "15 days ago\n", + "•\n", + "16.2k\n", + "•\n", + "415\n", + "Qwen/Qwen2.5-VL-32B-Instruct\n", + "Image-Text-to-Text\n", + "•\n", + "Updated\n", + "8 days ago\n", + "•\n", + "178k\n", + "•\n", + "310\n", + "google/gemma-3-27b-it\n", + "Image-Text-to-Text\n", + "•\n", + "Updated\n", + "13 days ago\n", + "•\n", + "953k\n", + "•\n", + "•\n", + "1.08k\n", + "Shakker-Labs/AWPortraitCN2\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "4 days ago\n", + "•\n", + "3.68k\n", + "•\n", + "74\n", + "Qwen/QwQ-32B\n", + "Text Generation\n", + "•\n", + "Updated\n", + "23 days ago\n", + "•\n", + "808k\n", + "•\n", + "•\n", + "2.62k\n", + "teapotai/teapotllm\n", + "Text2Text Generation\n", + "•\n", + "Updated\n", + "2 days ago\n", + "•\n", + "6.87k\n", + "•\n", + "•\n", + "140\n", + "VAST-AI/TripoSG\n", + "Image-to-3D\n", + "•\n", + "Updated\n", + "6 days ago\n", + "•\n", + "1.73k\n", + "•\n", + "69\n", + "unsloth/DeepSeek-V3-0324-GGUF\n", + "Text Generation\n", + "•\n", + "Updated\n", + "1 day ago\n", + "•\n", + "128k\n", + "•\n", + "140\n", + "canopylabs/orpheus-3b-0.1-ft\n", + "Text-to-Speech\n", + "•\n", + "Updated\n", + "15 days ago\n", + "•\n", + "45.8k\n", + "•\n", + "458\n", + "google/gemma-3-4b-it\n", + "Image-Text-to-Text\n", + "•\n", + "Updated\n", + "13 days ago\n", + "•\n", + "455k\n", + "•\n", + "395\n", + "mistralai/Mistral-Small-3.1-24B-Instruct-2503\n", + "Image-Text-to-Text\n", + "•\n", + "Updated\n", + "1 day ago\n", + "•\n", + "114k\n", + "•\n", + "1.04k\n", + "nomic-ai/nomic-embed-code\n", + "Sentence Similarity\n", + "•\n", + "Updated\n", + "3 days ago\n", + "•\n", + "1.29k\n", + "•\n", + "45\n", + "alibaba-pai/Wan2.1-Fun-1.3B-Control\n", + "Text-to-Video\n", + "•\n", + "Updated\n", + "3 days ago\n", + "•\n", + "6.16k\n", + "•\n", + "80\n", + "deepseek-ai/DeepSeek-V3\n", + "Text Generation\n", + "•\n", + "Updated\n", + "7 days ago\n", + "•\n", + "806k\n", + "•\n", + "•\n", + "3.78k\n", + "codermert/gamzekocc_fluxx\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "8 days ago\n", + "•\n", + "2.06k\n", + "•\n", + "•\n", + "91\n", + "stabilityai/stable-diffusion-3.5-large\n", + "Text-to-Image\n", + "•\n", + "Updated\n", + "Oct 22, 2024\n", + "•\n", + "130k\n", + "•\n", + "•\n", + "2.61k\n", + "System theme\n", + "Company\n", + "TOS\n", + "Privacy\n", + "About\n", + "Jobs\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Pricing\n", + "Docs\n", + "\n", + "\n", + "\n", + "products page\n", + "Webpage Title:\n", + "Hugging Face – The AI community building the future.\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Edit Datasets filters\n", + "Main\n", + "Tasks\n", + "Libraries\n", + "Languages\n", + "Licenses\n", + "Other\n", + "Modalities\n", + "3D\n", + "Audio\n", + "Geospatial\n", + "Image\n", + "Tabular\n", + "Text\n", + "Time-series\n", + "Video\n", + "Size\n", + "\t\t\t(rows)\n", + "Reset Size\n", + "< 1K\n", + "> 1T\n", + "Format\n", + "json\n", + "csv\n", + "parquet\n", + "imagefolder\n", + "soundfolder\n", + "webdataset\n", + "text\n", + "arrow\n", + "Apply filters\n", + "Datasets\n", + "347,395\n", + "Full-text search\n", + "Add filters\n", + "Sort: \n", + "\t\tTrending\n", + "nvidia/Llama-Nemotron-Post-Training-Dataset-v1\n", + "Viewer\n", + "•\n", + "Updated\n", + "16 days ago\n", + "•\n", + "15.2M\n", + "•\n", + "10.9k\n", + "•\n", + "300\n", + "FreedomIntelligence/medical-o1-reasoning-SFT\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 22\n", + "•\n", + "50.1k\n", + "•\n", + "24k\n", + "•\n", + "602\n", + "glaiveai/reasoning-v1-20m\n", + "Viewer\n", + "•\n", + "Updated\n", + "15 days ago\n", + "•\n", + "22.2M\n", + "•\n", + "8.87k\n", + "•\n", + "156\n", + "a-m-team/AM-DeepSeek-R1-Distilled-1.4M\n", + "Preview\n", + "•\n", + "Updated\n", + "4 days ago\n", + "•\n", + "8.59k\n", + "•\n", + "102\n", + "Anthropic/EconomicIndex\n", + "Viewer\n", + "•\n", + "Updated\n", + "7 days ago\n", + "•\n", + "3.36k\n", + "•\n", + "3.5k\n", + "•\n", + "242\n", + "virtuoussy/Multi-subject-RLVR\n", + "Viewer\n", + "•\n", + "Updated\n", + "1 day ago\n", + "•\n", + "579k\n", + "•\n", + "272\n", + "•\n", + "36\n", + "PixelAI-Team/TalkBody4D\n", + "Viewer\n", + "•\n", + "Updated\n", + "9 days ago\n", + "•\n", + "1.05M\n", + "•\n", + "83\n", + "•\n", + "66\n", + "Intelligent-Internet/II-Thought-RL-v0\n", + "Viewer\n", + "•\n", + "Updated\n", + "6 days ago\n", + "•\n", + "342k\n", + "•\n", + "2.98k\n", + "•\n", + "40\n", + "MrDragonFox/Elise\n", + "Viewer\n", + "•\n", + "Updated\n", + "7 days ago\n", + "•\n", + "1.2k\n", + "•\n", + "1.17k\n", + "•\n", + "22\n", + "Rapidata/OpenAI-4o_t2i_human_preference\n", + "Viewer\n", + "•\n", + "Updated\n", + "6 days ago\n", + "•\n", + "13k\n", + "•\n", + "837\n", + "•\n", + "28\n", + "MohamedRashad/Quran-Recitations\n", + "Viewer\n", + "•\n", + "Updated\n", + "4 days ago\n", + "•\n", + "125k\n", + "•\n", + "142\n", + "•\n", + "18\n", + "Congliu/Chinese-DeepSeek-R1-Distill-data-110k\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 21\n", + "•\n", + "110k\n", + "•\n", + "5.53k\n", + "•\n", + "608\n", + "HuggingFaceFW/fineweb\n", + "Viewer\n", + "•\n", + "Updated\n", + "Jan 31\n", + "•\n", + "25B\n", + "•\n", + "205k\n", + "•\n", + "2.08k\n", + "facebook/natural_reasoning\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 21\n", + "•\n", + "1.15M\n", + "•\n", + "11.6k\n", + "•\n", + "477\n", + "sychonix/emotion\n", + "Viewer\n", + "•\n", + "Updated\n", + "8 days ago\n", + "•\n", + "20k\n", + "•\n", + "635\n", + "•\n", + "27\n", + "openai/gsm8k\n", + "Viewer\n", + "•\n", + "Updated\n", + "Jan 4, 2024\n", + "•\n", + "17.6k\n", + "•\n", + "343k\n", + "•\n", + "675\n", + "fka/awesome-chatgpt-prompts\n", + "Viewer\n", + "•\n", + "Updated\n", + "Jan 6\n", + "•\n", + "203\n", + "•\n", + "11.2k\n", + "•\n", + "7.66k\n", + "X-ART/LeX-10K\n", + "Viewer\n", + "•\n", + "Updated\n", + "3 days ago\n", + "•\n", + "9.9k\n", + "•\n", + "1k\n", + "•\n", + "14\n", + "nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim\n", + "Updated\n", + "1 day ago\n", + "•\n", + "28.5k\n", + "•\n", + "102\n", + "Anthropic/hh-rlhf\n", + "Viewer\n", + "•\n", + "Updated\n", + "May 26, 2023\n", + "•\n", + "169k\n", + "•\n", + "13.1k\n", + "•\n", + "1.31k\n", + "open-r1/codeforces-cots\n", + "Viewer\n", + "•\n", + "Updated\n", + "6 days ago\n", + "•\n", + "254k\n", + "•\n", + "9.63k\n", + "•\n", + "125\n", + "cais/mmlu\n", + "Viewer\n", + "•\n", + "Updated\n", + "Mar 8, 2024\n", + "•\n", + "231k\n", + "•\n", + "142k\n", + "•\n", + "443\n", + "omar07ibrahim/Alpaca_Stanford_Azerbaijan\n", + "Viewer\n", + "•\n", + "Updated\n", + "Jan 23, 2024\n", + "•\n", + "19.2k\n", + "•\n", + "16\n", + "•\n", + "12\n", + "omar07ibrahim/alpaca-cleaned_AZERBAIJANI\n", + "Viewer\n", + "•\n", + "Updated\n", + "Jan 23, 2024\n", + "•\n", + "51.8k\n", + "•\n", + "28\n", + "•\n", + "13\n", + "omar07ibrahim/testlimOcrCA\n", + "Viewer\n", + "•\n", + "Updated\n", + "Jan 27, 2024\n", + "•\n", + "9\n", + "•\n", + "18\n", + "•\n", + "11\n", + "omar07ibrahim/azcon\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 22, 2024\n", + "•\n", + "237k\n", + "•\n", + "13\n", + "•\n", + "11\n", + "cais/hle\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 15\n", + "•\n", + "2.7k\n", + "•\n", + "6.35k\n", + "•\n", + "291\n", + "manycore-research/SpatialLM-Testset\n", + "Viewer\n", + "•\n", + "Updated\n", + "15 days ago\n", + "•\n", + "107\n", + "•\n", + "9.17k\n", + "•\n", + "51\n", + "inclusionAI/AReaL-boba-Data\n", + "Preview\n", + "•\n", + "Updated\n", + "5 days ago\n", + "•\n", + "263\n", + "•\n", + "11\n", + "Conard/fortune-telling\n", + "Viewer\n", + "•\n", + "Updated\n", + "Feb 17\n", + "•\n", + "207\n", + "•\n", + "5.75k\n", + "•\n", + "109\n", + "Previous\n", + "1\n", + "2\n", + "3\n", + "...\n", + "100\n", + "Next\n", + "System theme\n", + "Company\n", + "TOS\n", + "Privacy\n", + "About\n", + "Jobs\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Pricing\n", + "Docs\n", + "\n", + "\n", + "\n", + "products page\n", + "Webpage Title:\n", + "Spaces - Hugging Face\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Spaces\n", + "·\n", + "The AI App Directory\n", + "New Space\n", + "What is Spaces?\n", + "Image Generation\n", + "Video Generation\n", + "Text Generation\n", + "Language Translation\n", + "Speech Synthesis\n", + "3D Modeling\n", + "Object Detection\n", + "Text Analysis\n", + "Image Editing\n", + "Code Generation\n", + "Question Answering\n", + "Data Visualization\n", + "Voice Cloning\n", + "Background Removal\n", + "Image Upscaling\n", + "OCR\n", + "Document Analysis\n", + "Visual QA\n", + "Image Captioning\n", + "Chatbots\n", + "Sentiment Analysis\n", + "Text Summarization\n", + "Music Generation\n", + "Medical Imaging\n", + "Financial Analysis\n", + "Game AI\n", + "Model Benchmarking\n", + "Fine Tuning Tools\n", + "Dataset Creation\n", + "Pose Estimation\n", + "Face Recognition\n", + "Anomaly Detection\n", + "Recommendation Systems\n", + "Character Animation\n", + "Style Transfer\n", + "Image\n", + "Spaces of the week\n", + "31 Mar 2025\n", + "Sort: \n", + "\t\tRelevance\n", + "Running\n", + "on\n", + "Zero\n", + "268\n", + "TripoSG\n", + "🔮\n", + "Generate 3D models from images\n", + "VAST-AI\n", + "6 days ago\n", + "Running\n", + "215\n", + "Qwen2.5 Omni 7B Demo\n", + "🏆\n", + "Submit media inputs to generate text and speech responses\n", + "Qwen\n", + "7 days ago\n", + "Running\n", + "on\n", + "T4\n", + "73\n", + "CountGD_Multi-Modal_Open-World_Counting\n", + "🚀\n", + "Count objects in images using text or visual examples\n", + "nikigoli\n", + "17 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "254\n", + "Hi3DGen\n", + "🏢\n", + "High-fidelity 3D Geometry Generation from images\n", + "Stable-X\n", + "5 days ago\n", + "Running\n", + "1.95k\n", + "DeepSite\n", + "🐳\n", + "Generate any application with DeepSeek\n", + "enzostvs\n", + "about 5 hours ago\n", + "Running\n", + "216\n", + "starvector-1b-im2svg\n", + "📈\n", + "Convert images and text into scalable vector graphics (SVG) code\n", + "starvector\n", + "9 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "57\n", + "KDTalker\n", + "😛\n", + "Generate animated portraits from images and audio\n", + "fffiloni\n", + "8 days ago\n", + "Running\n", + "33\n", + "Expressive TTS Arena\n", + "🎤\n", + "Compare and vote on AI speech quality\n", + "HumeAI\n", + "10 days ago\n", + "All running apps, trending first\n", + "Running\n", + "1.95k\n", + "DeepSite\n", + "🐳\n", + "Generate any application with DeepSeek\n", + "enzostvs\n", + "about 5 hours ago\n", + "Running\n", + "on\n", + "Zero\n", + "365\n", + "EasyControl Ghibli\n", + "🦀\n", + "New Ghibli EasyControl model is now released!!\n", + "jamesliu1217\n", + "about 19 hours ago\n", + "Running\n", + "on\n", + "Zero\n", + "737\n", + "InfiniteYou-FLUX\n", + "📸\n", + "Flexible Photo Recrafting While Preserving Your Identity\n", + "ByteDance\n", + "1 day ago\n", + "Running\n", + "on\n", + "Zero\n", + "268\n", + "TripoSG\n", + "🔮\n", + "Generate 3D models from images\n", + "VAST-AI\n", + "6 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "254\n", + "Hi3DGen\n", + "🏢\n", + "High-fidelity 3D Geometry Generation from images\n", + "Stable-X\n", + "5 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "4.55k\n", + "TRELLIS\n", + "🏢\n", + "Scalable and Versatile 3D Generation from images\n", + "JeffreyXiang\n", + "Dec 18, 2024\n", + "Running\n", + "on\n", + "CPU Upgrade\n", + "8.19k\n", + "Kolors Virtual Try-On\n", + "👕\n", + "Overlay garment on person image\n", + "Kwai-Kolors\n", + "Sep 18, 2024\n", + "Running\n", + "215\n", + "Qwen2.5 Omni 7B Demo\n", + "🏆\n", + "Submit media inputs to generate text and speech responses\n", + "Qwen\n", + "7 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "1.27k\n", + "LuminaBrush\n", + "📈\n", + "Execute custom commands\n", + "lllyasviel\n", + "Dec 21, 2024\n", + "Running\n", + "931\n", + "InstantCoder\n", + "🦀\n", + "Generate app code from ideas\n", + "osanseviero\n", + "9 days ago\n", + "Running\n", + "216\n", + "starvector-1b-im2svg\n", + "📈\n", + "Convert images and text into scalable vector graphics (SVG) code\n", + "starvector\n", + "9 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "3.21k\n", + "IC Light V2\n", + "📈\n", + "Execute custom Python scripts from environment variables\n", + "lllyasviel\n", + "Oct 26, 2024\n", + "Running\n", + "on\n", + "Zero\n", + "2.2k\n", + "Hunyuan3D-2.0\n", + "🌍\n", + "Text-to-3D and Image-to-3D Generation\n", + "tencent\n", + "12 days ago\n", + "Running\n", + "on\n", + "CPU Upgrade\n", + "5.3k\n", + "MTEB Leaderboard\n", + "🥇\n", + "Embedding Leaderboard\n", + "mteb\n", + "6 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "275\n", + "LHM\n", + "⚡\n", + "Large Animatable Human Model\n", + "3DAIGC\n", + "about 9 hours ago\n", + "Running\n", + "386\n", + "Gemini Co-Drawing\n", + "✏\n", + "Gemini 2.0 native image generation co-doodling\n", + "Trudy\n", + "14 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "8.03k\n", + "FLUX.1 [dev]\n", + "🖥\n", + "Generate images from text prompts\n", + "black-forest-labs\n", + "1 day ago\n", + "Running\n", + "on\n", + "Zero\n", + "66\n", + "MV Adapter Img2Texture\n", + "🔮\n", + "Generate 3D texture from image\n", + "VAST-AI\n", + "3 days ago\n", + "Running\n", + "56\n", + "LLM Embeddings Explained: A Visual and Intuitive Guide\n", + "🚀\n", + "How Language Models Turn Text into Meaning, From Traditional\n", + "hesamation\n", + "6 days ago\n", + "Running\n", + "on\n", + "Zero\n", + "2.4k\n", + "Kokoro TTS\n", + "❤\n", + "Upgraded to v1.0!\n", + "hexgrad\n", + "16 days ago\n", + "Running\n", + "on\n", + "CPU Upgrade\n", + "9.84k\n", + "AI Comic Factory\n", + "👩\n", + "Create your own AI comic with a single prompt\n", + "jbilcke-hf\n", + "Oct 15, 2024\n", + "Running\n", + "145\n", + "WeShopAI Virtual Try On\n", + "👕\n", + "Transform flat-lay shots into on-model photos\n", + "WeShopAI\n", + "1 day ago\n", + "Running\n", + "on\n", + "Zero\n", + "57\n", + "KDTalker\n", + "😛\n", + "Generate animated portraits from images and audio\n", + "fffiloni\n", + "8 days ago\n", + "Running\n", + "2.4k\n", + "The Ultra-Scale Playbook\n", + "🌌\n", + "The ultimate guide to training LLM on large GPU Clusters\n", + "nanotron\n", + "23 days ago\n", + "Previous\n", + "1\n", + "2\n", + "3\n", + "...\n", + "100\n", + "Next\n", + "System theme\n", + "Company\n", + "TOS\n", + "Privacy\n", + "About\n", + "Jobs\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Pricing\n", + "Docs\n", + "\n", + "\n", + "\n", + "contact page\n", + "Webpage Title:\n", + "Hugging Face Forums - Hugging Face Community Discussion\n", + "Webpage Contents:\n", + "Hugging Face Forums\n", + "Topic\n", + "Replies\n", + "Views\n", + "Activity\n", + "Making a model \"think\" before doing a tool call (ReAct paper)\n", + "Research\n", + "0\n", + "18\n", + "April 3, 2025\n", + "Inference Provider\n", + "Beginners\n", + "0\n", + "8\n", + "April 3, 2025\n", + "Building a School AI: Encouraging Critical Thinking, Not Just Answers\n", + "Models\n", + "2\n", + "12\n", + "April 3, 2025\n", + "Confusion the code\n", + "Course\n", + "1\n", + "9\n", + "April 3, 2025\n", + "Floor plan segmentation\n", + "Beginners\n", + "2\n", + "13\n", + "April 3, 2025\n", + "Difference between pre-training and fine tuning with language modeling to instill new knowledge\n", + "🤗Transformers\n", + "1\n", + "10\n", + "April 3, 2025\n", + "How to Deploy an Vision Language model in azure?\n", + "Intermediate\n", + "1\n", + "5\n", + "April 3, 2025\n", + "Issues when trying to build llama.cpp\n", + "Beginners\n", + "7\n", + "18\n", + "April 3, 2025\n", + "Is there specific generative model to describe User Interfaces?\n", + "Models\n", + "4\n", + "26\n", + "April 2, 2025\n", + "DiffuserCraft STILL keeps acting up but this time, whenever I use it\n", + "Spaces\n", + "3\n", + "19\n", + "April 2, 2025\n", + "Wrong file is being downloaded\n", + "🤗Datasets\n", + "1\n", + "12\n", + "April 2, 2025\n", + "Exceeded your monthly included credits for Inference Providers\n", + "Intermediate\n", + "4\n", + "28\n", + "April 3, 2025\n", + "Wake word detection\n", + "Research\n", + "5\n", + "29\n", + "April 1, 2025\n", + "LORA Adapated Deepseek R1 not working with inference endpoints\n", + "Models\n", + "1\n", + "14\n", + "April 2, 2025\n", + "Unable to push agent to personal space from google colab value error\n", + "Course\n", + "3\n", + "16\n", + "April 3, 2025\n", + "Automating RAG Infrastructure Deployment with AI\n", + "Show and Tell\n", + "4\n", + "127\n", + "April 2, 2025\n", + "Huggingface pro subscription\n", + "Beginners\n", + "0\n", + "8\n", + "April 2, 2025\n", + "Changing the username more than twice\n", + "Beginners\n", + "1\n", + "13\n", + "April 1, 2025\n", + "Cannot export tflite using optimum for a fine-tuned gemma 3 model for task : question answering\n", + "Models\n", + "5\n", + "17\n", + "April 2, 2025\n", + "Pad token vs -100 index_id\n", + "Intermediate\n", + "2\n", + "17\n", + "April 1, 2025\n", + "Isn't there a simpler way to run LLMs / models locally?\n", + "Beginners\n", + "1\n", + "41\n", + "March 31, 2025\n", + "How to run Trainer + vLLM on Quantized LLMs?\n", + "Beginners\n", + "4\n", + "40\n", + "March 31, 2025\n", + "Using DistributedSampler with accelerate\n", + "🤗Transformers\n", + "4\n", + "20\n", + "April 2, 2025\n", + "I need a model for requirements extraction\n", + "Models\n", + "5\n", + "52\n", + "March 31, 2025\n", + "How to view more than 100 pages on the website\n", + "Beginners\n", + "1\n", + "25\n", + "April 1, 2025\n", + "How to get a list of all Huggingface download redirections to whitelist?\n", + "🤗Hub\n", + "14\n", + "6115\n", + "April 1, 2025\n", + "Help Creating a Custom GPT for a Futuristic Space RPG Campaign\n", + "Beginners\n", + "1\n", + "15\n", + "April 1, 2025\n", + "Help with DeepSeek-V3-0324 Model Download\n", + "Intermediate\n", + "4\n", + "44\n", + "April 3, 2025\n", + "Space: AttributeError: module 'gradio' has no attribute 'Sidebar'\n", + "Beginners\n", + "3\n", + "11\n", + "March 31, 2025\n", + "Help with image inpainting\n", + "Beginners\n", + "3\n", + "16\n", + "April 1, 2025\n", + "next page →\n", + "Home\n", + "Categories\n", + "Guidelines\n", + "Terms of Service\n", + "Privacy Policy\n", + "Powered by\n", + "Discourse\n", + ", best viewed with JavaScript enabled\n", + "\n", + "\n", + "\n", + "pricing page\n", + "Webpage Title:\n", + "Hugging Face – Pricing\n", + "Webpage Contents:\n", + "Hugging Face\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Posts\n", + "Docs\n", + "Enterprise\n", + "Pricing\n", + "Log In\n", + "Sign Up\n", + "Pricing\n", + "Leveling up AI collaboration and compute.\n", + "Users and organizations already use the Hub as a collaboration platform,\n", + "we’re making it easy to seamlessly and scalably launch ML compute directly from the Hub.\n", + "HF Hub\n", + "Collaborate on Machine Learning\n", + "Host unlimited public models, datasets\n", + "Create unlimited orgs with no member limits\n", + "Access the latest ML tools and open source\n", + "Community support\n", + "Forever\n", + "Free\n", + "PRO\n", + "Pro Account\n", + "Unlock advanced HF features\n", + "ZeroGPU and Dev Mode for Spaces\n", + "Free credits across all Inference Providers\n", + "Get early access to upcoming features\n", + "Show your support with a Pro badge\n", + "Subscribe for\n", + "$9\n", + "/month\n", + "Enterprise Hub\n", + "Accelerate your AI roadmap\n", + "SSO and SAML support\n", + "Select data location with Storage Regions\n", + "Precise actions reviews with Audit logs\n", + "Granular access control with Resource groups\n", + "Centralized token control and approval\n", + "Dataset Viewer for private datasets\n", + "Advanced compute options for Spaces\n", + "5x more ZeroGPU quota for all org members\n", + "Deploy Inference on your own Infra\n", + "Managed billing with yearly commits\n", + "Priority support\n", + "Starting at\n", + "$20\n", + "per user per month\n", + "Spaces Hardware\n", + "Upgrade your Space compute\n", + "Free CPUs\n", + "Build more advanced Spaces\n", + "7 optimized hardware available\n", + "From CPU to GPU to Accelerators\n", + "Starting at\n", + "$0\n", + "/hour\n", + "Inference Endpoints\n", + "Deploy models on fully managed infrastructure\n", + "Deploy dedicated Endpoints in seconds\n", + "Keep your costs low\n", + "Fully-managed autoscaling\n", + "Enterprise security\n", + "Starting at\n", + "$0.032\n", + "/hour\n", + "Need support to accelerate AI in your organization? View our\n", + "Expert Support\n", + ".\n", + "Hugging Face Hub\n", + "free\n", + "The HF Hub is the central place to explore, experiment, collaborate and build technology with Machine\n", + "\t\t\t\t\tLearning.\n", + "Join the open source Machine Learning movement!\n", + "→\n", + "Sign Up\n", + "Create with ML\n", + "Packed with ML features, like model eval, dataset viewer and much more.\n", + "Collaborate\n", + "Git based and designed for collaboration at its core.\n", + "Play and learn\n", + "Learn by experimenting and sharing with our awesome community.\n", + "Build your ML portfolio\n", + "Share your work with the world and build your own ML profile.\n", + "Spaces Hardware\n", + "Starting at $0\n", + "Spaces are one of the most popular ways to share ML applications and demos with the world.\n", + "Upgrade your Spaces with our selection of custom on-demand hardware:\n", + "→\n", + "Get started with Spaces\n", + "Name\n", + "CPU\n", + "Memory\n", + "Accelerator\n", + "VRAM\n", + "Hourly price\n", + "CPU Basic\n", + "2 vCPU\n", + "16 GB\n", + "-\n", + "-\n", + "FREE\n", + "CPU Upgrade\n", + "8 vCPU\n", + "32 GB\n", + "-\n", + "-\n", + "$0.03\n", + "Nvidia T4 - small\n", + "4 vCPU\n", + "15 GB\n", + "Nvidia T4\n", + "16 GB\n", + "$0.40\n", + "Nvidia T4 - medium\n", + "8 vCPU\n", + "30 GB\n", + "Nvidia T4\n", + "16 GB\n", + "$0.60\n", + "1x Nvidia L4\n", + "8 vCPU\n", + "30 GB\n", + "Nvidia L4\n", + "24 GB\n", + "$0.80\n", + "4x Nvidia L4\n", + "48 vCPU\n", + "186 GB\n", + "Nvidia L4\n", + "96 GB\n", + "$3.80\n", + "1x Nvidia L40S\n", + "8 vCPU\n", + "62 GB\n", + "Nvidia L4\n", + "48 GB\n", + "$1.80\n", + "4x Nvidia L40S\n", + "48 vCPU\n", + "382 GB\n", + "Nvidia L4\n", + "192 GB\n", + "$8.30\n", + "8x Nvidia L40S\n", + "192 vCPU\n", + "1534 GB\n", + "Nvidia L4\n", + "384 GB\n", + "$23.50\n", + "Nvidia A10G - small\n", + "4 vCPU\n", + "15 GB\n", + "Nvidia A10G\n", + "24 GB\n", + "$1.00\n", + "Nvidia A10G - large\n", + "12 vCPU\n", + "46 GB\n", + "Nvidia A10G\n", + "24 GB\n", + "$1.50\n", + "2x Nvidia A10G - large\n", + "24 vCPU\n", + "92 GB\n", + "Nvidia A10G\n", + "48 GB\n", + "$3.00\n", + "4x Nvidia A10G - large\n", + "48 vCPU\n", + "184 GB\n", + "Nvidia A10G\n", + "96 GB\n", + "$5.00\n", + "Nvidia A100 - large\n", + "12 vCPU\n", + "142 GB\n", + "Nvidia A100\n", + "80 GB\n", + "$4.00\n", + "Custom\n", + "on demand\n", + "on demand\n", + "on demand\n", + "on demand\n", + "on demand\n", + "Spaces Persistent Storage\n", + "All Spaces get ephemeral storage for free but you can upgrade and add persistent storage at any time.\n", + "Name\n", + "Storage\n", + "Monthly price\n", + "Small\n", + "20 GB\n", + "$5\n", + "Medium\n", + "150 GB\n", + "$25\n", + "Large\n", + "1 TB\n", + "$100\n", + "Building something cool as a side project? We also offer community GPU grants.\n", + "Inference Endpoints\n", + "Starting at $0.033/hour\n", + "Inference Endpoints (dedicated) offers a secure production solution to easily deploy any ML model on dedicated\n", + "\t\t\t\t\tand autoscaling infrastructure, right from the HF Hub.\n", + "→\n", + "Learn more\n", + "CPU\n", + "instances\n", + "Provider\n", + "Architecture\n", + "vCPUs\n", + "Memory\n", + "Hourly rate\n", + "aws\n", + "Intel Sapphire Rapids\n", + "1\n", + "2GB\n", + "$0.03\n", + "2\n", + "4GB\n", + "$0.07\n", + "4\n", + "8GB\n", + "$0.13\n", + "8\n", + "16GB\n", + "$0.27\n", + "16\n", + "32GB\n", + "$0.54\n", + "azure\n", + "Intel Xeon\n", + "1\n", + "2GB\n", + "$0.06\n", + "2\n", + "4GB\n", + "$0.12\n", + "4\n", + "8GB\n", + "$0.24\n", + "8\n", + "16GB\n", + "$0.48\n", + "gcp\n", + "Intel Sapphire Rapids\n", + "1\n", + "2GB\n", + "$0.05\n", + "2\n", + "4GB\n", + "$0.10\n", + "4\n", + "8GB\n", + "$0.20\n", + "8\n", + "16GB\n", + "$0.40\n", + "Accelerator\n", + "instances\n", + "Provider\n", + "Architecture\n", + "Topology\n", + "Accelerator Memory\n", + "Hourly rate\n", + "aws\n", + "Inf2\n", + "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tNeuron\n", + "x1\n", + "14.5GB\n", + "$0.75\n", + "x12\n", + "760GB\n", + "$12.00\n", + "gcp\n", + "TPU\n", + "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tv5e\n", + "1x1\n", + "16GB\n", + "$1.20\n", + "2x2\n", + "64GB\n", + "$4.75\n", + "2x4\n", + "128GB\n", + "$9.50\n", + "GPU\n", + "instances\n", + "Provider\n", + "Architecture\n", + "GPUs\n", + "GPU Memory\n", + "Hourly rate\n", + "aws\n", + "NVIDIA T4\n", + "1\n", + "14GB\n", + "$0.50\n", + "4\n", + "56GB\n", + "$3.00\n", + "aws\n", + "NVIDIA L4\n", + "1\n", + "24GB\n", + "$0.80\n", + "4\n", + "96GB\n", + "$3.80\n", + "aws\n", + "NVIDIA L40S\n", + "1\n", + "48GB\n", + "$1.80\n", + "4\n", + "192GB\n", + "$8.30\n", + "8\n", + "384GB\n", + "$23.50\n", + "aws\n", + "NVIDIA A10G\n", + "1\n", + "24GB\n", + "$1.00\n", + "4\n", + "96GB\n", + "$5.00\n", + "aws\n", + "NVIDIA A100\n", + "1\n", + "80GB\n", + "$4.00\n", + "2\n", + "160GB\n", + "$8.00\n", + "4\n", + "320GB\n", + "$16.00\n", + "8\n", + "640GB\n", + "$32.00\n", + "gcp\n", + "NVIDIA T4\n", + "1\n", + "16GB\n", + "$0.50\n", + "gcp\n", + "NVIDIA L4\n", + "1\n", + "24GB\n", + "$0.70\n", + "4\n", + "96GB\n", + "$3.80\n", + "gcp\n", + "NVIDIA A100\n", + "1\n", + "80GB\n", + "$3.60\n", + "2\n", + "160GB\n", + "$7.20\n", + "4\n", + "320GB\n", + "$14.40\n", + "8\n", + "640GB\n", + "$28.80\n", + "gcp\n", + "NVIDIA H100\n", + "1\n", + "80GB\n", + "$10.00\n", + "2\n", + "160GB\n", + "$20.00\n", + "4\n", + "320GB\n", + "$40.00\n", + "8\n", + "640GB\n", + "$80.00\n", + "Pro Account\n", + "PRO\n", + "A monthly subscription to access powerful features.\n", + "→\n", + "Get Pro\n", + "($9/month)\n", + "ZeroGPU\n", + ": Get 5x usage quota and highest GPU queue priority\n", + "Spaces Hosting\n", + ": Create ZeroGPU Spaces with A100 hardware\n", + "Spaces Dev Mode\n", + ": Fast iterations via SSH/VS Code for Spaces\n", + "Inference Providers\n", + ": Get $2 included credits across all Inference Providers\n", + "Dataset Viewer\n", + ": Activate it on private datasets\n", + "Blog Articles\n", + ": Publish articles to the Hugging Face blog\n", + "Social Posts\n", + ": Share short updates with the community\n", + "Features Preview\n", + ": Get early access to upcoming\n", + "\t\t\t\t\t\t\t\t\t\tfeatures\n", + "PRO\n", + "Badge\n", + ":\n", + "\t\t\t\t\t\t\t\t\t\tShow your support on your profile\n", + "System theme\n", + "Website\n", + "Models\n", + "Datasets\n", + "Spaces\n", + "Tasks\n", + "Inference Endpoints\n", + "HuggingChat\n", + "Company\n", + "About\n", + "Brand assets\n", + "Terms of service\n", + "Privacy\n", + "Jobs\n", + "Press\n", + "Resources\n", + "Learn\n", + "Documentation\n", + "Blog\n", + "Forum\n", + "Service Status\n", + "Social\n", + "GitHub\n", + "Twitter\n", + "LinkedIn\n", + "Discord\n", + "\n", + "\n" + ] + } + ], + "source": [ + "print(get_all_details(\"https://huggingface.co\"))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9b863a55-f86c-4e3f-8a79-94e24c1a8cf2", + "metadata": {}, + "outputs": [], + "source": [ + "#system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n", + "#and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n", + "#Include details of company culture, customers and careers/jobs if you have the information.\"\n", + "\n", + "# Or uncomment the lines below for a more humorous brochure - this demonstrates how easy it is to incorporate 'tone':\n", + "\n", + "system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n", + "and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n", + "Include details of company culture, customers and careers/jobs if you have the information.\"\n" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "id": "e93a46d5-c8f1-46c5-ad3f-8a21a0d2a4ad", + "metadata": {}, + "outputs": [], + "source": [ + "#2nd part of challenge\n", + "\n", + "# Structured prompt for generating the brochure\n", + "system_prompt = \"\"\"\n", + "You are an expert in marketing copywriting. Your task is to generate a structured company brochure \n", + "based on the provided company details and selected links. The brochure should be well-organized \n", + "and formatted into clear sections:\n", + "\n", + "**Structure of the brochure:**\n", + "\n", + "1. **Introduction** \n", + " - Provide a brief overview of the company, summarizing its key highlights.\n", + "\n", + "2. **About Us** \n", + " - Detail the company's background, mission, and core values. \n", + "\n", + "3. **Products & Services** \n", + " - List and describe the main products or services the company offers. \n", + "\n", + "4. **Careers** \n", + " - Mention any job opportunities, work culture, and hiring process if applicable. \n", + "\n", + "5. **Contact Information** \n", + " - Include ways to reach the company, such as website, email, and phone. \n", + "\n", + "**Formatting Guidelines:** \n", + "- Use clear section headings (e.g., \"About Us\", \"Products & Services\") \n", + "- Write in a professional and engaging tone. \n", + "- Keep the brochure concise yet informative. \n", + "\n", + "Generate the brochure following this structure.\n", + "\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6ab83d92-d36b-4ce0-8bcc-5bb4c2f8ff23", + "metadata": {}, + "outputs": [], + "source": [ + "def get_brochure_user_prompt(company_name, url):\n", + " user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n", + " user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n", + " user_prompt += get_all_details(url)\n", + " user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n", + " return user_prompt" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "cd909e0b-1312-4ce2-a553-821e795d7572", + "metadata": {}, + "outputs": [], + "source": [ + "get_brochure_user_prompt(\"HuggingFace\", \"https://huggingface.co\")" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "id": "e44de579-4a1a-4e6a-a510-20ea3e4b8d46", + "metadata": {}, + "outputs": [], + "source": [ + "def create_brochure(company_name, url):\n", + " response = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", + " ],\n", + " )\n", + " result = response.choices[0].message.content\n", + " display(Markdown(result))" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "id": "e093444a-9407-42ae-924a-145730591a39", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'products page', 'url': 'https://huggingface.co/models'}, {'type': 'products page', 'url': 'https://huggingface.co/datasets'}, {'type': 'products page', 'url': 'https://huggingface.co/spaces'}, {'type': 'contact page', 'url': 'https://huggingface.co/chat'}]}\n" + ] + }, + { + "data": { + "text/markdown": [ + "# Hugging Face Company Brochure\n", + "\n", + "## Introduction\n", + "Welcome to Hugging Face, the AI community building the future. Hugging Face is a pioneering platform where the machine learning community comes together to create, share, and collaborate on models, datasets, and applications. With more than 1 million models and a myriad of datasets, we empower developers, researchers, and innovators alike to accelerate their journey in AI and machine learning.\n", + "\n", + "## About Us\n", + "Founded with the mission to make machine learning accessible and collaborative, Hugging Face values openness, community, and innovation. Our platform is built on the belief that collective knowledge can drive progress in artificial intelligence, paving the way for advanced research and real-world applications. We pride ourselves on fostering a supportive and inclusive environment, where collaboration enhances the potential of each member.\n", + "\n", + "## Products & Services\n", + "Hugging Face offers a wide range of products and services:\n", + "\n", + "- **Models**: Access over 1 million high-quality machine learning models for various tasks including text, image, and audio processing.\n", + "- **Datasets**: Explore and utilize over 250,000 datasets to power your machine learning projects.\n", + "- **Spaces**: Collaborate and share applications within our user-friendly environment tailored for AI developers.\n", + "- **Enterprise Solutions**: Customized enterprise-grade services that provide advanced security and dedicated support starting at $20/user/month.\n", + "- **Open Source Tools**: Contribute to and leverage state-of-the-art tools like Transformers, Diffusers, and Tokenizers for research and production.\n", + "\n", + "## Careers\n", + "At Hugging Face, we are always on the lookout for passionate individuals to join our team. We promote a positive work culture that values collaboration, creativity, and continuous learning. If you're interested in being part of an innovative AI community, check out our careers page for current job openings and application details.\n", + "\n", + "## Contact Information\n", + "For more information, inquiries, or support, you can reach us at:\n", + "- **Website**: [huggingface.co](https://huggingface.co)\n", + "- **Email**: support@huggingface.co\n", + "- **Phone**: [insert phone number]\n", + "\n", + "Join us in building the future of AI! Together, we can empower the next generation of machine learning innovations." + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "create_brochure(\"HuggingFace\", \"https://huggingface.co\")" + ] + }, + { + "cell_type": "markdown", + "id": "61eaaab7-0b47-4b29-82d4-75d474ad8d18", + "metadata": {}, + "source": [ + "## Finally - a minor improvement\n", + "\n", + "With a small adjustment, we can change this so that the results stream back from OpenAI,\n", + "with the familiar typewriter animation" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "id": "51db0e49-f261-4137-aabe-92dd601f7725", + "metadata": {}, + "outputs": [], + "source": [ + "def stream_brochure(company_name, url):\n", + " stream = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", + " ],\n", + " stream=True\n", + " )\n", + " \n", + " response = \"\"\n", + " display_handle = display(Markdown(\"\"), display_id=True)\n", + " for chunk in stream:\n", + " response += chunk.choices[0].delta.content or ''\n", + " response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n", + " update_display(Markdown(response), display_id=display_handle.display_id)" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "id": "56bf0ae3-ee9d-4a72-9cd6-edcac67ceb6d", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co/'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'products page', 'url': 'https://huggingface.co/models'}, {'type': 'products page', 'url': 'https://huggingface.co/datasets'}, {'type': 'contact page', 'url': 'https://huggingface.co/chat'}]}\n" + ] + }, + { + "data": { + "text/markdown": [ + "\n", + "# Hugging Face Company Brochure\n", + "\n", + "## Introduction\n", + "Welcome to Hugging Face, the AI community dedicated to building the future through collaboration and innovation. As a leader in the machine learning community, we offer a platform for individuals and organizations to create, discover, and collaborate on cutting-edge models, datasets, and applications.\n", + "\n", + "## About Us\n", + "Hugging Face is on a mission to advance the field of machine learning by fostering collaboration among its members. Our core values revolve around open-source technology, community participation, and accessibility. We believe that together, we can build tools that leverage artificial intelligence for the benefit of all. With over 50,000 organizations leveraging our platform, Hugging Face is setting the pace in the AI space.\n", + "\n", + "## Products & Services\n", + "At Hugging Face, we provide a robust range of products and services:\n", + "\n", + "- **Models**: Access a library with over 1 million models including state-of-the-art machine learning tools for PyTorch, TensorFlow, and JAX.\n", + "- **Datasets**: Explore and share 250,000+ datasets suitable for various ML tasks, which can enhance your machine learning projects.\n", + "- **Spaces**: Create and run applications effortlessly with thousands of ready-to-use ML applications available on our platform.\n", + "- **Enterprise Solutions**: Tailored for businesses, our enterprise solutions come with advanced features such as security, compliance, and dedicated support.\n", + " \n", + "Whether you are a researcher, developer, or business leader, we have resources to accelerate your machine learning initiatives.\n", + "\n", + "## Careers\n", + "Join the Hugging Face community! We are looking for passionate individuals committed to shaping the future of AI. We offer a dynamic work environment that encourages innovation and collaboration. Check our careers page for current job openings and become part of our journey in transforming artificial intelligence.\n", + "\n", + "## Contact Information\n", + "Ready to explore more? Reach out to us through the following channels:\n", + "\n", + "- **Website**: [Hugging Face](https://huggingface.co)\n", + "- **Email**: contact@huggingface.co\n", + "- **Phone**: +1 (800) 123-4567\n", + "\n", + "Connect with us on our social platforms: [GitHub](https://github.com/huggingface), [Twitter](https://twitter.com/huggingface), [LinkedIn](https://www.linkedin.com/company/huggingface), [Discord](https://discord.gg/huggingface).\n", + "\n", + "---\n", + "\n", + "Take the next step in your AI journey with Hugging Face today!\n", + "\n" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fdb3f8d8-a3eb-41c8-b1aa-9f60686a653b", + "metadata": {}, + "outputs": [], + "source": [ + "# Try changing the system prompt to the humorous version when you make the Brochure for Hugging Face:\n", + "\n", + "stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "id": "fb7cca18-4bf7-4676-a5f5-ad5b6ea92c65", + "metadata": {}, + "outputs": [], + "source": [ + "#3rd part of challenge\n", + "\n", + "def translate_brochure(brochure_content, language=\"Spanish\"):\n", + " system_prompt = f\"You are a skilled translator. Translate the following brochure text into {language}. \\\n", + " Ensure the translation is idiomatic, matching the target language's natural structure, expressions, and nuances. \\\n", + " The translated version should feel native and not like a direct translation. \\\n", + " Adapt the tone appropriately—marketing language in {language} should be engaging yet culturally suitable. \\\n", + " Output the translated brochure in Markdown format. \\\n", + " \"\n", + " response = openai.chat.completions.create(\n", + " model=MODEL,\n", + " messages=[\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": brochure_content}\n", + " ],\n", + " )\n", + " result = response.choices[0].message.content\n", + " display(Markdown(result))" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "id": "ba4840bf-1559-4eeb-9cd1-a733ebaa214a", + "metadata": {}, + "outputs": [ + { + "data": { + "text/markdown": [ + "# Hugging Face\n", + "\n", + "## Bienvenidos a la comunidad de Hugging Face\n", + "\n", + "En Hugging Face, creemos que el desarrollo de la inteligencia artificial debe ser accesible para todos. Nuestra misión es democratizar el acceso y la comprensión de la IA, permitiendo a desarrolladores, investigadores y empresas construir soluciones innovadoras. \n", + "\n", + "### ¿Qué ofrecemos?\n", + "\n", + "- **Modelos preentrenados**: Descubre una amplia biblioteca de modelos de procesamiento de lenguaje natural que pueden ser adaptados a tus necesidades específicas. Desde traducciones hasta generación de texto, tenemos todo cubierto.\n", + "\n", + "- **Herramientas fáciles de usar**: Con nuestras herramientas, podrás integrar IA en tus proyectos de manera sencilla, sin necesidad de ser un experto. Empezar es muy fácil y rápido.\n", + "\n", + "- **Comunidad activa**: Únete a una vibrante comunidad de entusiastas de la IA. Comparte tus ideas, aprende de otros y colabora en proyectos emocionantes.\n", + "\n", + "### ¿Por qué elegir Hugging Face?\n", + "\n", + "- **Innovación constante**: Estamos a la vanguardia de la investigación en IA y actualizamos regularmente nuestra plataforma para ofrecerte lo último en tecnología.\n", + "\n", + "- **Soporte excepcional**: Nuestro equipo está aquí para ayudarte. Ofrecemos asistencia y recursos para que puedas sacar el máximo provecho de nuestras soluciones.\n", + "\n", + "- **Compromiso con la ética**: Nos tomamos en serio la responsabilidad social y trabajamos con un enfoque ético para garantizar que nuestro trabajo tenga un impacto positivo en la sociedad.\n", + "\n", + "### ¡Únete a nosotros hoy!\n", + "\n", + "Visita nuestra página web y descubre cómo Hugging Face puede transformar tus proyectos con inteligencia artificial. Juntos, ¡haré del mundo un lugar más inteligente y conectado!\n", + "\n", + "---\n", + "\n", + "En Hugging Face, el futuro de la IA está al alcance de tu mano. ¡Empecemos este emocionante viaje juntos!" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "None\n" + ] + } + ], + "source": [ + "spanish_brochure = translate_brochure(\"Hugging Face\", \"Spanish\")\n", + "print(spanish_brochure)" + ] + }, + { + "cell_type": "markdown", + "id": "a27bf9e0-665f-4645-b66b-9725e2a959b5", + "metadata": {}, + "source": [ + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \n", + "

Business applications

\n", + " In this exercise we extended the Day 1 code to make multiple LLM calls, and generate a document.\n", + "\n", + "This is perhaps the first example of Agentic AI design patterns, as we combined multiple calls to LLMs. This will feature more in Week 2, and then we will return to Agentic AI in a big way in Week 8 when we build a fully autonomous Agent solution.\n", + "\n", + "Generating content in this way is one of the very most common Use Cases. As with summarization, this can be applied to any business vertical. Write marketing content, generate a product tutorial from a spec, create personalized email content, and so much more. Explore how you can apply content generation to your business, and try making yourself a proof-of-concept prototype. See what other students have done in the community-contributions folder -- so many valuable projects -- it's wild!\n", + "
" + ] + }, + { + "cell_type": "markdown", + "id": "14b2454b-8ef8-4b5c-b928-053a15e0d553", + "metadata": {}, + "source": [ + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \n", + "

Before you move to Week 2 (which is tons of fun)

\n", + " Please see the week1 EXERCISE notebook for your challenge for the end of week 1. This will give you some essential practice working with Frontier APIs, and prepare you well for Week 2.\n", + "
" + ] + }, + { + "cell_type": "markdown", + "id": "17b64f0f-7d33-4493-985a-033d06e8db08", + "metadata": {}, + "source": [ + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \n", + "

A reminder on 3 useful resources

\n", + " 1. The resources for the course are available here.
\n", + " 2. I'm on LinkedIn here and I love connecting with people taking the course!
\n", + " 3. I'm trying out X/Twitter and I'm at @edwarddonner and hoping people will teach me how it's done.. \n", + "
\n", + "
" + ] + }, + { + "cell_type": "markdown", + "id": "6f48e42e-fa7a-495f-a5d4-26bfc24d60b6", + "metadata": {}, + "source": [ + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \n", + "

Finally! I have a special request for you

\n", + " \n", + " My editor tells me that it makes a MASSIVE difference when students rate this course on Udemy - it's one of the main ways that Udemy decides whether to show it to others. If you're able to take a minute to rate this, I'd be so very grateful! And regardless - always please reach out to me at ed@edwarddonner.com if I can help at any point.\n", + " \n", + "
" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b8d3e1a1-ba54-4907-97c5-30f89a24775b", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}